Medical Image Processing Apparatus, Medical Image Processing System, and Medical Image Processing Method

1. A medical image processing apparatus comprising: a memory configured to store a predetermined program; and processing circuitry configured, by executing the predetermined program, to acquire a plurality of images that are obtained by imaging a same object and are different in imaging time, classify respective regions of the plurality of images into a plurality of texture patterns by performing texture analysis based on pixel values of the respective regions of the plurality of images, assign the classified texture patterns to the respective regions of the plurality of the images, and estimate change in disease state of the object from change in the texture patterns in respectively corresponding regions of the plurality of the images, wherein the plurality of images are images of a lung field of the object, and the plurality of texture patterns include at least one of a ground-glass opacities pattern, a reticular and linear opacities pattern, a nodular opacities pattern, a honeycombing pattern, and a consolidation pattern.

2. The medical image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to estimate change in disease state for each of the corresponding regions, and generate a map image by determining respective pixel values of the map image in such a manner that change in disease state is distinguishably depicted for each of the corresponding regions in any one of the plurality of images.

3. The medical image processing apparatus according to claim 1 , wherein the processing circuitry is configured to estimate the change in disease state and rate of the change in disease state in the respectively corresponding regions of the plurality of images, based on change in the texture patterns in the respectively corresponding regions of the plurality of images.

4. The medical image processing apparatus according to claim 1 , wherein the processing circuitry is configured to acquire a first image and a second image, the first image being imaged at a first date and time, and the second image being imaged at a second date and time after the first date and time, classify respective regions of the first image and the second image into the plurality of texture patterns, and estimate whether a change direction of the disease state in local regions of the object is recovery, exacerbation, or no change, by using change in the texture patterns in respectively corresponding local regions of the first image and the second image.

5. The medical image processing apparatus according to claim 4 , wherein the processing circuitry is configured to estimate the change direction of the disease state for every pixel or for every pixel group consisting of two or more pixels.

6. The medical image processing apparatus according to claim 4 , further comprising a display, wherein the processing circuitry is configured to generate a disease-state-change map in which the change direction of the disease state is depicted for every pixel or for every pixel group consisting of two or more pixels, and cause the display to display the disease-state-change map.

7. The medical image processing apparatus according to claim 6 , wherein the processing circuitry is configured to generate the disease-state-change map in such a manner that the disease state is distinguishably depicted for every pixel or for every pixel group, with different manners including at least one of different chromatic colors, different grayscale, different numbers, and different signs.

8. The medical image processing apparatus according to claim 4 , wherein: the memory is configured to further store a lookup table in which types of the texture patterns are associated with degree of progression of the disease state; and the processing circuitry is configured to estimate the change direction of the disease state by referring to the lookup table.

9. The medical image processing apparatus according to claim 8 , wherein the processing circuitry is configured to further estimate at least one of recovery rate in a recovery direction and exacerbation rate in an exacerbation direction by referring to the lookup table.

10. The medical image processing apparatus according to claim 8 , wherein: the memory is configured to further store lookup tables respectively corresponding to different disease causes, each of the lookup tables being a lookup table in which types of the texture patterns are associated with degree of progression of the disease state; and the processing circuitry is configured to estimate the change direction of the disease state based on one of the lookup tables corresponding to a disease designated by a user.

11. The medical image processing apparatus according to claim 10 , wherein the processing circuitry is configured to further estimate a disease cause of the object from change in the texture patterns in respectively corresponding local regions of the first image and the second image, based on the lookup tables respectively corresponding to different disease causes.

12. The medical image processing apparatus according to claim 8 , wherein the processing circuitry is configured to update contents of the lookup table stored in the memory through user operation.

13. A medical image processing system comprising: processing circuitry configured to acquire a plurality of images that are obtained by imaging a same object and are different in imaging time, classify respective regions of the plurality of images into a plurality of texture patterns by performing texture analysis based on pixel values of the respective regions of the plurality of images, assign the classified texture patterns to the respective regions of the plurality of the images, and estimate change in disease state of the object from change in the texture patterns in respectively corresponding regions of the plurality of the images, wherein the plurality of images are images of a lung field of the object, and the plurality of texture patterns include at least one of a ground-glass opacities pattern, a reticular and linear opacities pattern, a nodular opacities pattern, a honeycombing pattern, and a consolidation pattern.

14. A medical image processing method comprising: acquiring a plurality of images that are obtained by imaging a same object and are different in imaging time; classifying respective regions of the plurality of images into a plurality of texture patterns by performing texture analysis based on pixel values of the respective regions of the plurality of images; assigning the classified texture patterns to the respective regions of the plurality of images; and estimating change in disease state of the object from change in the texture patterns in respectively corresponding regions of the plurality of images, wherein the plurality of images are images of a lung field of the object, and the plurality of texture patterns include at least one of a ground-glass opacities pattern, a reticular and linear opacities pattern, a nodular opacities pattern, a honeycombing pattern, and a consolidation pattern.